search

kotalikg / cuda-convnet

Automatically exported from code.google.com/p/cuda-convnet
0 stars 0 forks source link

Getting nan values while using response normalization layer #8

Open GoogleCodeExporter opened 9 years ago

GoogleCodeExporter commented 9 years ago 
The network training is fine without adding any contrast normalization layer 
(all types), but ones add the contrast normalization layers, after several 
iterations the net gets nan values.  I tried different values of the size, 
scale and pow values, and tried to place the layer before and after pooling 
layer.

Original issue reported on code.google.com by zybzm...@gmail.com on 8 May 2013 at 7:44

GoogleCodeExporter commented 9 years ago 
I have a similar issue. Does it still work when you remove the contrast 
normalization layer?

Original comment by olivern...@gmail.com on 13 Sep 2013 at 7:30